End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,96 @@
+---
+base_model: xxxxxxxxx
+tags:
+- generated_from_trainer
+datasets:
+- AmazonScience/massive
+metrics:
+- f1
+model-index:
+- name: massive_indo
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# massive_indo
+
+This model is a fine-tuned version of [xxxxxxxxx](https://huggingface.co/xxxxxxxxx) on the massive dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0967
+- F1: 0.8702
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.747         | 1.39  | 500   | 1.0303          | 0.5703 |
+| 0.5618        | 2.78  | 1000  | 0.9201          | 0.6479 |
+| 0.3695        | 4.17  | 1500  | 0.8216          | 0.6990 |
+| 0.3392        | 5.56  | 2000  | 0.7637          | 0.7335 |
+| 0.2638        | 6.94  | 2500  | 0.8244          | 0.7678 |
+| 0.1907        | 8.33  | 3000  | 0.7912          | 0.7979 |
+| 0.1661        | 9.72  | 3500  | 0.8266          | 0.7835 |
+| 0.1073        | 11.11 | 4000  | 0.8120          | 0.8139 |
+| 0.1265        | 12.5  | 4500  | 0.8336          | 0.8344 |
+| 0.0481        | 13.89 | 5000  | 0.8240          | 0.8518 |
+| 0.0646        | 15.28 | 5500  | 0.9290          | 0.8333 |
+| 0.0846        | 16.67 | 6000  | 0.9176          | 0.8461 |
+| 0.0228        | 18.06 | 6500  | 0.9600          | 0.8529 |
+| 0.0696        | 19.44 | 7000  | 0.9769          | 0.8525 |
+| 0.0614        | 20.83 | 7500  | 0.9944          | 0.8545 |
+| 0.0173        | 22.22 | 8000  | 1.0110          | 0.8550 |
+| 0.004         | 23.61 | 8500  | 1.0140          | 0.8417 |
+| 0.0032        | 25.0  | 9000  | 1.0771          | 0.8314 |
+| 0.0453        | 26.39 | 9500  | 1.0173          | 0.8424 |
+| 0.0471        | 27.78 | 10000 | 1.0068          | 0.8652 |
+| 0.0128        | 29.17 | 10500 | 1.0595          | 0.8658 |
+| 0.0027        | 30.56 | 11000 | 1.0596          | 0.8506 |
+| 0.0198        | 31.94 | 11500 | 1.0468          | 0.8593 |
+| 0.0027        | 33.33 | 12000 | 1.0537          | 0.8693 |
+| 0.0114        | 34.72 | 12500 | 1.0512          | 0.8620 |
+| 0.015         | 36.11 | 13000 | 1.0425          | 0.8813 |
+| 0.005         | 37.5  | 13500 | 1.1092          | 0.8749 |
+| 0.0038        | 38.89 | 14000 | 1.0829          | 0.8637 |
+| 0.0096        | 40.28 | 14500 | 1.0902          | 0.8794 |
+| 0.0007        | 41.67 | 15000 | 1.0994          | 0.8651 |
+| 0.0109        | 43.06 | 15500 | 1.0957          | 0.8782 |
+| 0.0026        | 44.44 | 16000 | 1.0997          | 0.8643 |
+| 0.0061        | 45.83 | 16500 | 1.0853          | 0.8672 |
+| 0.0005        | 47.22 | 17000 | 1.1082          | 0.8694 |
+| 0.0005        | 48.61 | 17500 | 1.1016          | 0.8696 |
+| 0.0028        | 50.0  | 18000 | 1.0967          | 0.8702 |
+
+
+### Framework versions
+
+- Transformers 4.34.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.0

config.json

@@ -0,0 +1,151 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057fb1c9056a49672ebbbd9220ea5ca448d261dd454514d521c6eaad69f5ae67
+size 470775793

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb652ac4e40cc093272bbbe0f55d521cf67570060227109b5cdc20945a4489e
+size 17098107

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae0ac2b16e3d4faa7152cd113f4673d28a7ea2c6a4c747aaedb806dfc28d116
+size 3963